© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4488
    Prev
    Next
    INDEX
    Explanations

    expressions and phrases indicating certainty or clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Affirmations or confirmations (yes, sure, right)

    np_acts-logits-general · gemini-2.0-flash

    confirmation or agreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IKit
    -0.48
    ⋙
    -0.47
    hésite
    -0.45
    embe
    -0.45
    нгредіє
    -0.44
    Slu
    -0.44
    CIT
    -0.44
    expandindo
    -0.44
     MZ
    -0.44
    Pitt
    -0.43
    POSITIVE LOGITS
    这一点
    0.47
    这点
    0.44
    XmlIgnore
    0.38
     isso
    0.38
     ça
    0.38
     Spitze
    0.36
     garansi
    0.36
    esModule
    0.36
     Darauf
    0.35
    TypedDataSet
    0.34
    Activations Density 0.300%

    No Known Activations